Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1872 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.6568. Min Act: 0.0000

Data Index: 1335759 (The Pile)

Max Activating Token Index: 559

Text #1

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1782389 (The Pile)

Max Activating Token Index: 6

Text #2

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1255720 (The Pile)

Max Activating Token Index: 978

Text #3

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5499. Min Act: -0.0000

Data Index: 277594 (The Pile)

Max Activating Token Index: 306

Text #4

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5632. Min Act: -0.0000

Data Index: 1782795 (The Pile)

Max Activating Token Index: 172

Text #5

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1241983 (The Pile)

Max Activating Token Index: 274

Text #6

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5605. Min Act: 0.0000

Data Index: 1451656 (The Pile)

Max Activating Token Index: 357

Text #7

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5399. Min Act: 0.0000

Data Index: 319862 (The Pile)

Max Activating Token Index: 532

Text #8

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5727. Min Act: -0.0000

Data Index: 1164738 (The Pile)

Max Activating Token Index: 651

Text #9

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1528894 (The Pile)

Max Activating Token Index: 748

Text #10

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5538. Min Act: -0.0000

Data Index: 1880751 (The Pile)

Max Activating Token Index: 779

Text #11

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5732. Min Act: -0.0000

Data Index: 970196 (The Pile)

Max Activating Token Index: 512

Text #12

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5361. Min Act: 0.0000

Data Index: 40007 (The Pile)

Max Activating Token Index: 638

Text #13

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1814730 (The Pile)

Max Activating Token Index: 311

Text #14

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1155381 (The Pile)

Max Activating Token Index: 201

Text #15

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5206. Min Act: -0.0000

Data Index: 366685 (The Pile)

Max Activating Token Index: 230

Text #16

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5674. Min Act: 0.0000

Data Index: 1670444 (The Pile)

Max Activating Token Index: 121

Text #17

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5271. Min Act: 0.0000

Data Index: 546658 (The Pile)

Max Activating Token Index: 838

Text #18

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5185. Min Act: 0.0000

Data Index: 1573258 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1250975 (The Pile)

Max Activating Token Index: 6